compositor.inspect

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered by structured data. The description adds 'Risk: read; maturity: L3' which provides some context about the operation's risk level and maturity classification. However, it doesn't disclose what the inspection actually does, what state it reads, or what the output contains. The description doesn't contradict the annotations, but it adds minimal behavioral context beyond them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very short—two sentences—but the first sentence is largely redundant with the tool name and title. The second sentence about argument checks and session policy is generic harness boilerplate that doesn't add tool-specific value. It's concise but not informative; the brevity is achieved by omitting substance rather than by efficient writing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema and safe annotations, the description fails to explain what the compositor inspection returns or what aspect of the compositor it examines. The tool has zero required parameters and no description of what 'inspect' means in this context. An agent cannot predict what this tool does or what it will receive back. The output schema exists but the description should still orient the agent on what is being inspected and why they'd use it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 75% (3 of 4 parameters have descriptions), and the parameters are all harness infrastructure fields (_requestId, _authorization, _transactionId, _expectedSceneRevision) that are self-explanatory from their names and descriptions. The description adds no parameter-specific meaning, but the schema already documents these adequately. The _expectedSceneRevision parameter lacks a description, but its name is reasonably self-explanatory. Baseline 3 is appropriate since the schema carries the burden.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description says 'PartMe Blender Harness command `compositor.inspect`' which is essentially a tautology—it restates the tool name and title without explaining what 'inspect' does, what resource it inspects, or what information it returns. The name suggests inspecting the Blender compositor, but the description never states the verb's object or the inspection's purpose, making it hard to distinguish from other inspect tools like blender_render_inspect or blender_sequence_inspect.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It mentions 'Per-request argument checks and session policy still apply' which is generic harness boilerplate, not usage guidance. With many sibling inspect tools (blender_scene_inspect, blender_rig_inspect, blender_tracking_inspect, etc.), an agent has no way to know when compositor.inspect is the right choice.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.